sgonzalezsilot commited on
Commit
57ebd99
1 Parent(s): 3e56af5

End of training

Browse files
Files changed (4) hide show
  1. README.md +65 -0
  2. config.json +27 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: digitalepidemiologylab/covid-twitter-bert-v2
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: output
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # output
17
+
18
+ This model is a fine-tuned version of [digitalepidemiologylab/covid-twitter-bert-v2](https://huggingface.co/digitalepidemiologylab/covid-twitter-bert-v2) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0995
21
+ - F1: 0.9843
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 0.0127 | 1.0 | 321 | 0.0817 | 0.9781 |
53
+ | 0.0716 | 2.0 | 642 | 0.1124 | 0.9788 |
54
+ | 0.0716 | 3.0 | 963 | 0.0804 | 0.9843 |
55
+ | 0.0255 | 4.0 | 1284 | 0.1176 | 0.9820 |
56
+ | 0.008 | 5.0 | 1605 | 0.1065 | 0.9820 |
57
+ | 0.008 | 6.0 | 1926 | 0.0995 | 0.9843 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.37.2
63
+ - Pytorch 2.1.0+cu121
64
+ - Datasets 2.16.1
65
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "digitalepidemiologylab/covid-twitter-bert-v2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.37.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b57e768f7aaf759d5b83c117b3495e1ba7762b34cfc7e7fe4c823f5d447872
3
+ size 1340622760
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de15315b953722759f5da3c5534c74e3c30299ad6cc5b88bec2a147af19af4d
3
+ size 4664